haystack/test/test_utils.py

72 lines
2.3 KiB
Python
Raw Normal View History

[RAG] Integrate "Retrieval-Augmented Generation" with Haystack (#484) * Adding dummy generator implementation * Adding tutorial to try the model * Committing current non working code * Committing current update where we need to call generate function directly and need to convert embedding to tensor way * Addressing review comments. * Refactoring finder, and implementing rag_generator class. * Refined the implementation of RAGGenerator and now it is in clean shape * Renaming RAGGenerator to RAGenerator * Reverting change from finder.py and addressing review comments * Remove support for RagSequenceForGeneration * Utilizing embed_passage function from DensePassageRetriever * Adding sample test data to verify generator output * Updating testing script * Updating testing script * Fixing bug related to top_k * Updating latest farm dependency * Comment out farm dependency * Reverting changes from TransformersReader * Adding transformers dataset to compare transformers and haystack generator implementation * Using generator_encoder instead of question_encoder to generate context_input_ids * Adding workaround to install FARM dependency from master branch * Removing unnecessary changes * Fixing generator test * Removing transformers datasets * Fixing generator test * Some cleanup and updating TODO comments * Adding tutorial notebook * Updating tutorials with comments * Explicitly passing token model in RAG test * Addressing review comments * Fixing notebook * Refactoring tests to reduce memory footprint * Split generator tests in separate ci step and before running it reclaim memory by terminating containers * Moving tika dependent test to separate dir * Remove unwanted code * Brining reader under session scope * Farm is now session object hence restoring changes from default value * Updating assert for pdf converter * Dummy commit to trigger CI flow * REducing memory footprint required for generator tests * Fixing mypy issues * Marking test with tika and elasticsearch markers. Reverting changes in CI and pytest splits * reducing changes * Fixing CI * changing elastic search ci * Fixing test error * Disabling return of embedding * Marking generator test as well * Refactoring tutorials * Increasing ES memory to 750M * Trying another fix for ES CI * Reverting CI changes * Splitting tests in CI * Generator and non-generator markers split * Adding pytest.ini to add markers and enable strict-markers option * Reducing elastic search container memory * Simplifying generator test by using documents with embedding directly * Bump up farm to 0.5.0
2020-10-30 18:06:02 +01:00
import pytest
import pandas as pd
from pathlib import Path
[RAG] Integrate "Retrieval-Augmented Generation" with Haystack (#484) * Adding dummy generator implementation * Adding tutorial to try the model * Committing current non working code * Committing current update where we need to call generate function directly and need to convert embedding to tensor way * Addressing review comments. * Refactoring finder, and implementing rag_generator class. * Refined the implementation of RAGGenerator and now it is in clean shape * Renaming RAGGenerator to RAGenerator * Reverting change from finder.py and addressing review comments * Remove support for RagSequenceForGeneration * Utilizing embed_passage function from DensePassageRetriever * Adding sample test data to verify generator output * Updating testing script * Updating testing script * Fixing bug related to top_k * Updating latest farm dependency * Comment out farm dependency * Reverting changes from TransformersReader * Adding transformers dataset to compare transformers and haystack generator implementation * Using generator_encoder instead of question_encoder to generate context_input_ids * Adding workaround to install FARM dependency from master branch * Removing unnecessary changes * Fixing generator test * Removing transformers datasets * Fixing generator test * Some cleanup and updating TODO comments * Adding tutorial notebook * Updating tutorials with comments * Explicitly passing token model in RAG test * Addressing review comments * Fixing notebook * Refactoring tests to reduce memory footprint * Split generator tests in separate ci step and before running it reclaim memory by terminating containers * Moving tika dependent test to separate dir * Remove unwanted code * Brining reader under session scope * Farm is now session object hence restoring changes from default value * Updating assert for pdf converter * Dummy commit to trigger CI flow * REducing memory footprint required for generator tests * Fixing mypy issues * Marking test with tika and elasticsearch markers. Reverting changes in CI and pytest splits * reducing changes * Fixing CI * changing elastic search ci * Fixing test error * Disabling return of embedding * Marking generator test as well * Refactoring tutorials * Increasing ES memory to 750M * Trying another fix for ES CI * Reverting CI changes * Splitting tests in CI * Generator and non-generator markers split * Adding pytest.ini to add markers and enable strict-markers option * Reducing elastic search container memory * Simplifying generator test by using documents with embedding directly * Bump up farm to 0.5.0
2020-10-30 18:06:02 +01:00
Add CI for windows runner (#1458) * Feat: Removing use of temp file while downloading archive from url along with adding CI for windows and mac platform * Windows CI by default installing pytorch gpu hence updating CI to pick cpu version * fixing mac cache build issue * updating windows pip install command for torch * another attempt * updating ci * Adding sudo * fixing ls failure on windows * another attempt to fix build issue * Saving env variable of test files * Adding debug log * Github action differ on windows * adding debug * anohter attempt * Windows have different ways to receive env * fixing template * minor fx * Adding debug * Removing use of json * Adding back fromJson * addin toJson * removing print * anohter attempt * disabling parallel run at least for testing * installing docker for mac runner * correcting docker install command * Linux dockers are not suported in windows * Removing mac changes * Upgrading pytorch * using lts pytorch * Separating win and ubuntu * Install java 11 * enabling linux container env * docker cli command * docker cli command * start elastic service * List all service * correcting service name * Attempt to fix multiple test run * convert to json * another attempt to check * Updating build cache step * attempt * Add tika * Separating windows CI * Changing CI name * Skipping test which does not work in windows * Skipping tests for windows * create cleanup function in conftest * adding skipif marker on tests * Run windows PR on only push to master * Addressing review comments * Enabling windows ci for this PR * Tika init is being called when importing tika function * handling tika import issue * handling tika import issue in test * Fixing import issue * removing tika fixure * Removing fixture from tests * Disable windows ci on pull request * Add back extra pytorch install step Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2021-10-29 13:52:28 +05:30
from haystack.utils.preprocessing import convert_files_to_dicts, tika_convert_files_to_dicts
from haystack.utils.cleaning import clean_wiki_text
from haystack.utils.augment_squad import augment_squad
from haystack.utils.squad_data import SquadData
Pipeline's YAML: syntax validation (#2226) * Add BasePipeline.validate_config, BasePipeline.validate_yaml, and some new custom exception classes * Make error composition work properly * Clarify typing * Help mypy a bit more * Update Documentation & Code Style * Enable autogenerated docs for Milvus1 and 2 separately * Revert "Enable autogenerated docs for Milvus1 and 2 separately" This reverts commit 282be4a78a6e95862a9b4c924fc3dea5ca71e28d. * Update Documentation & Code Style * Re-enable 'additionalProperties: False' * Add pipeline.type to JSON Schema, was somehow forgotten * Disable additionalProperties on the pipeline properties too * Fix json-schemas for 1.1.0 and 1.2.0 (should not do it again in the future) * Cal super in PipelineValidationError * Improve _read_pipeline_config_from_yaml's error handling * Fix generate_json_schema.py to include document stores * Fix json schemas (retro-fix 1.1.0 again) * Improve custom errors printing, add link to docs * Add function in BaseComponent to list its subclasses in a module * Make some document stores base classes abstract * Add marker 'integration' in pytest flags * Slighly improve validation of pipelines at load * Adding tests for YAML loading and validation * Make custom_query Optional for validation issues * Fix bug in _read_pipeline_config_from_yaml * Improve error handling in BasePipeline and Pipeline and add DAG check * Move json schema generation into haystack/nodes/_json_schema.py (useful for tests) * Simplify errors slightly * Add some YAML validation tests * Remove load_from_config from BasePipeline, it was never used anyway * Improve tests * Include json-schemas in package * Fix conftest imports * Make BasePipeline abstract * Improve mocking by making the test independent from the YAML version * Add exportable_to_yaml decorator to forget about set_config on mock nodes * Fix mypy errors * Comment out one monkeypatch * Fix typing again * Improve error message for validation * Add required properties to pipelines * Fix YAML version for REST API YAMLs to 1.2.0 * Fix load_from_yaml call in load_from_deepset_cloud * fix HaystackError.__getattr__ * Add super().__init__()in most nodes and docstore, comment set_config * Remove type from REST API pipelines * Remove useless init from doc2answers * Call super in Seq3SeqGenerator * Typo in deepsetcloud.py * Fix rest api indexing error mismatch and mock version of JSON schema in all tests * Working on pipeline tests * Improve errors printing slightly * Add back test_pipeline.yaml * _json_schema.py supports different versions with identical schemas * Add type to 0.7 schema for backwards compatibility * Fix small bug in _json_schema.py * Try alternative to generate json schemas on the CI * Update Documentation & Code Style * Make linux CI match autoformat CI * Fix super-init-not-called * Accidentally committed file * Update Documentation & Code Style * fix test_summarizer_translation.py's import * Mock YAML in a few suites, split and simplify test_pipeline_debug_and_validation.py::test_invalid_run_args * Fix json schema for ray tests too * Update Documentation & Code Style * Reintroduce validation * Usa unstable version in tests and rest api * Make unstable support the latest versions * Update Documentation & Code Style * Remove needless fixture * Make type in pipeline optional in the strings validation * Fix schemas * Fix string validation for pipeline type * Improve validate_config_strings * Remove type from test p[ipelines * Update Documentation & Code Style * Fix test_pipeline * Removing more type from pipelines * Temporary CI patc * Fix issue with exportable_to_yaml never invoking the wrapped init * rm stray file * pipeline tests are green again * Linux CI now needs .[all] to generate the schema * Bugfixes, pipeline tests seems to be green * Typo in version after merge * Implement missing methods in Weaviate * Trying to avoid FAISS tests from running in the Milvus1 test suite * Fix some stray test paths and faiss index dumping * Fix pytest markers list * Temporarily disable cache to be able to see tests failures * Fix pyproject.toml syntax * Use only tmp_path * Fix preprocessor signature after merge * Fix faiss bug * Fix Ray test * Fix documentation issue by removing quotes from faiss type * Update Documentation & Code Style * use document properly in preprocessor tests * Update Documentation & Code Style * make preprocessor capable of handling documents * import document * Revert support for documents in preprocessor, do later * Fix bug in _json_schema.py that was breaking validation * re-enable cache * Update Documentation & Code Style * Simplify calling _json_schema.py from the CI * Remove redundant ABC inheritance * Ensure exportable_to_yaml works only on implementations * Rename subclass to class_ in Meta * Make run() and get_config() abstract in BasePipeline * Revert unintended change in preprocessor * Move outgoing_edges_input_node check inside try block * Rename VALID_CODE_GEN_INPUT_REGEX into VALID_INPUT_REGEX * Add check for a RecursionError on validate_config_strings * Address usages of _pipeline_config in data silo and elasticsearch * Rename _pipeline_config into _init_parameters * Fix pytest marker and remove unused imports * Remove most redundant ABCs * Rename _init_parameters into _component_configuration * Remove set_config and type from _component_configuration's dict * Remove last instances of set_config and replace with super().__init__() * Implement __init_subclass__ approach * Simplify checks on the existence of _component_configuration * Fix faiss issue * Dynamic generation of node schemas & weed out old schemas * Add debatable test * Add docstring to debatable test * Positive diff between schemas implemented * Improve diff printing * Rename REST API YAML files to trigger IDE validation * Fix typing issues * Fix more typing * Typo in YAML filename * Remove needless type:ignore * Add tests * Fix tests & validation feedback for accessory classes in custom nodes * Refactor RAGeneratorType out * Fix broken import in conftest * Improve source error handling * Remove unused import in test_eval.py breaking tests * Fix changed error message in tests matches too * Normalize generate_openapi_specs.py and generate_json_schema.py in the actions * Fix path to generate_openapi_specs.py in autoformat.yml * Update Documentation & Code Style * Add test for FAISSDocumentStore-like situations (superclass with init params) * Update Documentation & Code Style * Fix indentation * Remove commented set_config * Store model_name_or_path in FARMReader to use in DistillationDataSilo * Rename _component_configuration into _component_config * Update Documentation & Code Style Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-03-15 11:17:26 +01:00
from .conftest import SAMPLES_PATH
Add CI for windows runner (#1458) * Feat: Removing use of temp file while downloading archive from url along with adding CI for windows and mac platform * Windows CI by default installing pytorch gpu hence updating CI to pick cpu version * fixing mac cache build issue * updating windows pip install command for torch * another attempt * updating ci * Adding sudo * fixing ls failure on windows * another attempt to fix build issue * Saving env variable of test files * Adding debug log * Github action differ on windows * adding debug * anohter attempt * Windows have different ways to receive env * fixing template * minor fx * Adding debug * Removing use of json * Adding back fromJson * addin toJson * removing print * anohter attempt * disabling parallel run at least for testing * installing docker for mac runner * correcting docker install command * Linux dockers are not suported in windows * Removing mac changes * Upgrading pytorch * using lts pytorch * Separating win and ubuntu * Install java 11 * enabling linux container env * docker cli command * docker cli command * start elastic service * List all service * correcting service name * Attempt to fix multiple test run * convert to json * another attempt to check * Updating build cache step * attempt * Add tika * Separating windows CI * Changing CI name * Skipping test which does not work in windows * Skipping tests for windows * create cleanup function in conftest * adding skipif marker on tests * Run windows PR on only push to master * Addressing review comments * Enabling windows ci for this PR * Tika init is being called when importing tika function * handling tika import issue * handling tika import issue in test * Fixing import issue * removing tika fixure * Removing fixture from tests * Disable windows ci on pull request * Add back extra pytorch install step Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2021-10-29 13:52:28 +05:30
def test_convert_files_to_dicts():
documents = convert_files_to_dicts(
dir_path=(SAMPLES_PATH).absolute(), clean_func=clean_wiki_text, split_paragraphs=True
)
assert documents and len(documents) > 0
[RAG] Integrate "Retrieval-Augmented Generation" with Haystack (#484) * Adding dummy generator implementation * Adding tutorial to try the model * Committing current non working code * Committing current update where we need to call generate function directly and need to convert embedding to tensor way * Addressing review comments. * Refactoring finder, and implementing rag_generator class. * Refined the implementation of RAGGenerator and now it is in clean shape * Renaming RAGGenerator to RAGenerator * Reverting change from finder.py and addressing review comments * Remove support for RagSequenceForGeneration * Utilizing embed_passage function from DensePassageRetriever * Adding sample test data to verify generator output * Updating testing script * Updating testing script * Fixing bug related to top_k * Updating latest farm dependency * Comment out farm dependency * Reverting changes from TransformersReader * Adding transformers dataset to compare transformers and haystack generator implementation * Using generator_encoder instead of question_encoder to generate context_input_ids * Adding workaround to install FARM dependency from master branch * Removing unnecessary changes * Fixing generator test * Removing transformers datasets * Fixing generator test * Some cleanup and updating TODO comments * Adding tutorial notebook * Updating tutorials with comments * Explicitly passing token model in RAG test * Addressing review comments * Fixing notebook * Refactoring tests to reduce memory footprint * Split generator tests in separate ci step and before running it reclaim memory by terminating containers * Moving tika dependent test to separate dir * Remove unwanted code * Brining reader under session scope * Farm is now session object hence restoring changes from default value * Updating assert for pdf converter * Dummy commit to trigger CI flow * REducing memory footprint required for generator tests * Fixing mypy issues * Marking test with tika and elasticsearch markers. Reverting changes in CI and pytest splits * reducing changes * Fixing CI * changing elastic search ci * Fixing test error * Disabling return of embedding * Marking generator test as well * Refactoring tutorials * Increasing ES memory to 750M * Trying another fix for ES CI * Reverting CI changes * Splitting tests in CI * Generator and non-generator markers split * Adding pytest.ini to add markers and enable strict-markers option * Reducing elastic search container memory * Simplifying generator test by using documents with embedding directly * Bump up farm to 0.5.0
2020-10-30 18:06:02 +01:00
@pytest.mark.tika
Add CI for windows runner (#1458) * Feat: Removing use of temp file while downloading archive from url along with adding CI for windows and mac platform * Windows CI by default installing pytorch gpu hence updating CI to pick cpu version * fixing mac cache build issue * updating windows pip install command for torch * another attempt * updating ci * Adding sudo * fixing ls failure on windows * another attempt to fix build issue * Saving env variable of test files * Adding debug log * Github action differ on windows * adding debug * anohter attempt * Windows have different ways to receive env * fixing template * minor fx * Adding debug * Removing use of json * Adding back fromJson * addin toJson * removing print * anohter attempt * disabling parallel run at least for testing * installing docker for mac runner * correcting docker install command * Linux dockers are not suported in windows * Removing mac changes * Upgrading pytorch * using lts pytorch * Separating win and ubuntu * Install java 11 * enabling linux container env * docker cli command * docker cli command * start elastic service * List all service * correcting service name * Attempt to fix multiple test run * convert to json * another attempt to check * Updating build cache step * attempt * Add tika * Separating windows CI * Changing CI name * Skipping test which does not work in windows * Skipping tests for windows * create cleanup function in conftest * adding skipif marker on tests * Run windows PR on only push to master * Addressing review comments * Enabling windows ci for this PR * Tika init is being called when importing tika function * handling tika import issue * handling tika import issue in test * Fixing import issue * removing tika fixure * Removing fixture from tests * Disable windows ci on pull request * Add back extra pytorch install step Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2021-10-29 13:52:28 +05:30
def test_tika_convert_files_to_dicts():
documents = tika_convert_files_to_dicts(dir_path=SAMPLES_PATH, clean_func=clean_wiki_text, split_paragraphs=True)
assert documents and len(documents) > 0
def test_squad_augmentation():
input_ = SAMPLES_PATH / "squad" / "tiny.json"
output = SAMPLES_PATH / "squad" / "tiny_augmented.json"
glove_path = SAMPLES_PATH / "glove" / "tiny.txt" # dummy glove file, will not even be use when augmenting tiny.json
multiplication_factor = 5
augment_squad(
model="distilbert-base-uncased",
tokenizer="distilbert-base-uncased",
squad_path=input_,
output_path=output,
glove_path=glove_path,
multiplication_factor=multiplication_factor,
)
original_squad = SquadData.from_file(input_)
augmented_squad = SquadData.from_file(output)
assert original_squad.count(unit="paragraph") == augmented_squad.count(unit="paragraph") * multiplication_factor
def test_squad_to_df():
df = pd.DataFrame(
[["title", "context", "question", "id", "answer", 1, False]],
columns=["title", "context", "question", "id", "answer_text", "answer_start", "is_impossible"],
)
expected_result = [
{
"title": "title",
"paragraphs": [
{
"context": "context",
"qas": [
{
"question": "question",
"id": "id",
"answers": [{"text": "answer", "answer_start": 1}],
"is_impossible": False,
}
],
}
],
}
]
result = SquadData.df_to_data(df)
assert result == expected_result